Smart vehicle floor sensor
Methods and apparatus consistent with the present disclosure may use a plurality of force sensing devices that allow a computer of an autonomous vehicle (AV) to identify locations within the AV where particular objects reside. These force sensing devices may allow the AV computer to identify how much a particular object weights and identify whether an object has moved based on a location where a particular amount of weight currently resides versus a location where that weight previously resided in the AV. Weight information combined with other sensor data (e.g. camera or LIDAR data) may allow the AV computer to identify whether a particular object is a person or a package. The AV computer may also validate that certain driving rules are enforced, such that persons or packages are being moved safely and correctly in the AV.
1 . A method comprising:
accessing first sensor data captured by one or more floor weight sensors of a vehicle at a first time;
identifying a weight associated with an object in the vehicle from the first sensor data;
identifying a weight distribution on a floor of the vehicle associated with the object from the first sensor data;
identifying a reference location of the object on the floor of the vehicle at the first time based on the weight and the weight distribution identified from the first sensor data;
accessing second sensor data captured by the one or more floor weight sensors at a second time;
identifying a second location of the object on the floor of the vehicle at the second time based on the weight, the weight distribution, and the second sensor data; and
tracking movement of the object relative to the reference location within the vehicle based on the weight distribution, the reference location, the second location, the first time, and the second time.
2 . The method of claim 1 , wherein the reference location of the object is within a container secured to the floor of the vehicle and the tracking of the movement of the object includes tracking removal of the object from the container and out of an exit of the vehicle.
3 . The method of claim 2 , wherein the container is configured to store multiple objects and the vehicle is configured to deliver the multiple objects to one or more delivery locations.
4 . The method of claim 1 , wherein the object is an occupant of the vehicle, the method further comprising:
identifying a pattern of movement of the occupant in the vehicle from the tracked movement of the occupant relative to the reference location; and
determining a behavior of the occupant in association with the vehicle based on the pattern of movement.
5 . The method of claim 4 , wherein the vehicle is an autonomous vehicle, and the method further comprising controlling operation of the autonomous vehicle based on the behavior of the occupant in association with the vehicle.
6 . The method of claim 4 , further comprising:
comparing the pattern of movement of the occupant in the vehicle with patterns of movements of occupants in vehicles associated with the vehicle; and
detecting abnormalities in the behavior of the occupant in relation to behaviors of the occupants based on a comparison of the pattern of movement of the occupant in the vehicle with the patterns of movements of the occupants in the vehicles associated with the vehicle.
7 . The method of claim 1 , further comprising:
accessing additional sensor data of one or more other types of sensors of the vehicle with respect to the one or more floor weight sensors; and
tracking the movement of the object relative to the reference location within the vehicle based on both the first sensor data and the additional sensor data.
8 . The method of claim 1 , further comprising determining a stability of the object within the vehicle based on the tracked movement of the object relative to the reference location.
9 . The method of claim 8 , wherein the vehicle is an autonomous vehicle, and the method further comprises controlling operation of the autonomous vehicle based on the stability of the object within the autonomous vehicle.
10 . The method of claim 1 , wherein the one or more floor weight sensors include a plurality of force sensors spaced at known locations corresponding to defined spatial subsets of the floor of the vehicle.
11 . A system comprising:
one or more floor weight sensors of a vehicle configured to capture sensor data;
one or more processors; and
at least one computer-readable storage medium having stored therein instructions which, when executed by the one or more processors, cause the one or more processors to:
access first sensor data captured by the one or more floor weight sensors of the vehicle at a first time;
identify a weight associated with an object in the vehicle from the first sensor data;
identify a weight distribution on a floor of the vehicle associated with the object from the first sensor data;
identify a reference location of the object on the floor of the vehicle at the first time based on the weight and the weight distribution identified from the first sensor data;
access second sensor data captured by the one or more floor weight sensors at a second time;
identify a second location of the object on the floor of the vehicle at the second time based on the weight, the weight distribution, and the second sensor data; and
track movement of the object relative to the reference location within the vehicle based on the weight distribution, the reference location, the second location, the first time, and the second time.
12 . The system of claim 11 , wherein the one or more floor weight sensors include a plurality of force sensors spaced at known locations corresponding to defined spatial subsets of the floor of the vehicle.
13 . The system of claim 11 , wherein the one or more floor weight sensors include one or more scanning sensors.
14 . The system of claim 11 , further comprising:
a camera from which camera data is received.
15 . The system of claim 14 , wherein the instructions also cause the one or more processors to identify an object type to associate with the object based at least in part on an evaluation of the camera data.
16 . The system of claim 11 , further comprising:
a light detection and ranging (LIDAR) device from which LIDAR data is received.
17 . The system of claim 16 , wherein the instructions also cause the one or more processors to identify an object type to associate with the object based at least in part on an evaluation of the LIDAR data.
18 . The system of claim 11 , further comprising:
one or more seat force sensors configured to identify presence of additional objects on one or more seats of the vehicle.
19 . The system of claim 11 , further comprising:
a delivery compartment into which the object is placed.
20 . A non-transitory computer-readable storage medium having stored therein instructions which, when executed by one or more processors, cause the one or more processors to:
access first sensor data captured by one or more floor weight sensors of a vehicle at a first time;
identify a weight associated with an object in the vehicle from the first sensor data;
identify a weight distribution on a floor of the vehicle associated with the object from the first sensor data;
identify a reference location of the object on the floor of the vehicle at the first time based on the weight and the weight distribution identified from the first sensor data;
access second sensor data captured by the one or more floor weight sensors at a second time;
identify a second location of the object on the floor of the vehicle at the second time based on the weight, the weight distribution, and the second sensor data; and
track movement of the object relative to the reference location within the vehicle based on the weight distribution, the reference location, the second location, the first time, and the second time.